What are alternative lemmas and what do we do with them?

Two main cases to consider.

  1. Compound words: For a compound word such as Samstagmorgen, it's nice to get three lemmas: Samstagmorgen, Samstag, Morgen. 
  2. Ambiguity: When POS is ambiguous (e.g. we don't have enough text to figure it out, say at query time) lemmas for all possible POS values are returned. For example for the word 'spoke' in isolation, the lemmas would be 'speak' and 'spoke'.


Was this article helpful?
0 out of 0 found this helpful
Have more questions? Submit a request


Please sign in to leave a comment.

Powered by Zendesk